Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d8cb96055200f7fdc5f50bb43fa392335a4f9d2e7ba2afd0090c7c11b0f300
+oid sha256:6368c6e8b866d0433bcdc13650505995205ccdf44f87672dcedb23e6daa69a4a
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:021df7de41040c695a767332330c9ac7416abb1f342852cf4143c8c130ea176d
+oid sha256:2466cd0cf8dc099207e5f20b11b00bc5ac82a2453d4b5a91c6e8f026cfdd3cb2
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee1097baacecf79408b42ee144bd460309ea0d1d52ffbbf1f1e6176bab5a92f5
+oid sha256:3b6a75a118df3adb6100390221238e779dd8d9f08dc08edd0fd65968f09a82ac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15015015015015015,
+  "epoch": 0.3003003003003003,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 2.3664,
       "step": 25
+    },
+    {
+      "epoch": 0.15615615615615616,
+      "grad_norm": 0.6066960096359253,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.2977,
+      "step": 26
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 0.682429850101471,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.2791,
+      "step": 27
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "eval_loss": 1.1289162635803223,
+      "eval_runtime": 20.9937,
+      "eval_samples_per_second": 6.669,
+      "eval_steps_per_second": 0.857,
+      "step": 27
+    },
+    {
+      "epoch": 0.16816816816816818,
+      "grad_norm": 0.5853718519210815,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.2462,
+      "step": 28
+    },
+    {
+      "epoch": 0.17417417417417416,
+      "grad_norm": 0.681626558303833,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.2603,
+      "step": 29
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 0.6157286763191223,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.2548,
+      "step": 30
+    },
+    {
+      "epoch": 0.18618618618618618,
+      "grad_norm": 0.5568789839744568,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.1607,
+      "step": 31
+    },
+    {
+      "epoch": 0.1921921921921922,
+      "grad_norm": 0.7827078700065613,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.268,
+      "step": 32
+    },
+    {
+      "epoch": 0.1981981981981982,
+      "grad_norm": 0.6743062734603882,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.0744,
+      "step": 33
+    },
+    {
+      "epoch": 0.2042042042042042,
+      "grad_norm": 0.7264645099639893,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.1957,
+      "step": 34
+    },
+    {
+      "epoch": 0.21021021021021022,
+      "grad_norm": 0.7725199460983276,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.2592,
+      "step": 35
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.6977213025093079,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.1857,
+      "step": 36
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "eval_loss": 1.095693588256836,
+      "eval_runtime": 20.957,
+      "eval_samples_per_second": 6.68,
+      "eval_steps_per_second": 0.859,
+      "step": 36
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.5948267579078674,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.1454,
+      "step": 37
+    },
+    {
+      "epoch": 0.22822822822822822,
+      "grad_norm": 0.5648744106292725,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.0381,
+      "step": 38
+    },
+    {
+      "epoch": 0.23423423423423423,
+      "grad_norm": 0.6770027279853821,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.2106,
+      "step": 39
+    },
+    {
+      "epoch": 0.24024024024024024,
+      "grad_norm": 0.6534614562988281,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.1378,
+      "step": 40
+    },
+    {
+      "epoch": 0.24624624624624625,
+      "grad_norm": 0.5991220474243164,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.2575,
+      "step": 41
+    },
+    {
+      "epoch": 0.25225225225225223,
+      "grad_norm": 0.6903526186943054,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.1784,
+      "step": 42
+    },
+    {
+      "epoch": 0.25825825825825827,
+      "grad_norm": 0.5913608074188232,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.1488,
+      "step": 43
+    },
+    {
+      "epoch": 0.26426426426426425,
+      "grad_norm": 0.6624292135238647,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.1639,
+      "step": 44
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.8672691583633423,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.2637,
+      "step": 45
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "eval_loss": 1.072501540184021,
+      "eval_runtime": 20.9263,
+      "eval_samples_per_second": 6.69,
+      "eval_steps_per_second": 0.86,
+      "step": 45
+    },
+    {
+      "epoch": 0.27627627627627627,
+      "grad_norm": 0.6573371887207031,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1309,
+      "step": 46
+    },
+    {
+      "epoch": 0.2822822822822823,
+      "grad_norm": 0.7428563833236694,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.1847,
+      "step": 47
+    },
+    {
+      "epoch": 0.2882882882882883,
+      "grad_norm": 0.5846123695373535,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.2138,
+      "step": 48
+    },
+    {
+      "epoch": 0.29429429429429427,
+      "grad_norm": 0.6415207982063293,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.2448,
+      "step": 49
+    },
+    {
+      "epoch": 0.3003003003003003,
+      "grad_norm": 0.5973365902900696,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.0774,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.347789697024e+16,
+  "total_flos": 1.2695579394048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null